© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107496
    Prev
    Next
    INDEX
    Explanations

    Internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adol
    -0.31
    çĪ¬ä¸Ĭ
    -0.29
    atty
    -0.28
    ay
    -0.27
    -images
    -0.27
     Rows
    -0.25
     Plumbing
    -0.25
     Drill
    -0.24
    åıĶ
    -0.24
    alez
    -0.24
    POSITIVE LOGITS
    oji
    0.27
    YY
    0.27
    ãĥ¥
    0.26
    åIJĪ
    0.25
    åħ·ä½ĵ
    0.24
    æĢ»ä¹ĭ
    0.24
     overall
    0.23
    lement
    0.23
    istring
    0.23
    æĢ»ä½ĵ
    0.23
    Activations Density 16.807%

    No Known Activations